Transcript 下載/瀏覽
多媒體網路安全實驗室
Ontological recommendation
multi-agent for Tainan City travel
Date:2012.11.20
Speaker : Hong Ji Wei
Authors : Chang-Shing , Lee,Young-Chung Chang, Mei-Hui Wang
From : Expert Systems with Applications on Elsevier
Vol. 36, pp. 6740–6753, 2009
多媒體網路安全實驗室
OUTLINE
1
INTRODUCTION
2
THE STRUCTURE OF TAINAN TRAVEL ONTOLOGY
3
CONTEXT DECISION AGENT FOR TAINAN TRAVEL
4
35
TRAVEL ROUTE RECOMMENDATION AGENT
FOR TAINAN CITY TRAVEL
CONCLUSION
1
多媒體網路安全實驗室
1. INTRODUCTION
In recent years, due to the growing number of travelers, a
wide range of information such as the tourist attractions and
local gourmet food are posted on the Internet to appeal to
the tourists.
It is not easy for a tourist to search the information what
exactly he really wants from a large amount of information
available on the Internet.
Ontology is a conceptualization of a domain into a human
understandable, machine-readable format consisting of
entities, attributes, relationships, and axioms
2
多媒體網路安全實驗室
2. THE STRUCTURE OF TAINAN
TRAVEL ONTOLOGY
2.1. Ontology Structure
The domain ontology architecture can be divided into four
layers.
1. Domain Layer
This layer defines name of the ontology.
2. Category Layer
This layer defines several categories such as category 1, category 2.
3. Concept Layer
This layer defines concept name, attribute set and operation set.
4. Instance Layer
This layer defines the instances of concept.
3
多媒體網路安全實驗室
2. THE STRUCTURE OF TAINAN
TRAVEL ONTOLOGY
4
多媒體網路安全實驗室
2. THE STRUCTURE OF TAINAN
TRAVEL ONTOLOGY
2.2. Tainan City travel ontology
The domain name of this ontology is "Tainan City Travel".
The categories in the category layer include "Administrative
District", "Historic Site Class", "Gourmet Food Type", and
"Rating Popularity Grade".
多媒體網路安全實驗室
2. THE STRUCTURE OF TAINAN
TRAVEL ONTOLOGY
6
多媒體網路安全實驗室
2. THE STRUCTURE OF TAINAN
TRAVEL ONTOLOGY
7
多媒體網路安全實驗室
2. THE STRUCTURE OF TAINAN
TRAVEL ONTOLOGY
8
多媒體網路安全實驗室
3. CONTEXT DECISION AGENT
FOR TAINAN TRAVEL
9
多媒體網路安全實驗室
3. CONTEXT DECISION AGENT
FOR TAINAN TRAVEL
The context decision agent contains following mechanisms
1. Location transfer mechanism.
2. Finding matched concepts mechanism.
3. Ant colony optimization for semantic relation mechanism.
4. Context relation computation mechanism.
10
多媒體網路安全實驗室
3. CONTEXT DECISION AGENT
FOR TAINAN TRAVEL
3.1. Location transfer mechanism
The main functions of this mechanism are to acquire the
location value of each concept.
11
多媒體網路安全實驗室
3. CONTEXT DECISION AGENT
FOR TAINAN TRAVEL
3.2. Finding matched concepts mechanism
The finding matched concepts mechanism is responsible for
finding the concepts matched with the tourist’s requirements.
12
多媒體網路安全實驗室
3. CONTEXT DECISION AGENT
FOR TAINAN TRAVEL
3.3. Ant colony optimization for semantic relation mechanism
The main function of the ant colony optimization for
semantic relation mechanism is to find the semantic relation
based on the found path of concepts between the ontology
and tourist’s requirements.
13
多媒體網路安全實驗室
3. CONTEXT DECISION AGENT
FOR TAINAN TRAVEL
3.4. Context relation computation mechanism
The context relation computation mechanism is to compute
the context relation between the tourist‘s requirements and
the instances stored in the ontology.
14
多媒體網路安全實驗室
4. TRAVEL ROUTE RECOMMENDATION AGENT
FOR TAINAN CITY TRAVEL
15
多媒體網路安全實驗室
4. TRAVEL ROUTE RECOMMENDATION AGENT
FOR TAINAN CITY TRAVEL
16
多媒體網路安全實驗室
4. TRAVEL ROUTE RECOMMENDATION AGENT
FOR TAINAN CITY TRAVEL
17
多媒體網路安全實驗室
CONCLUSION
The proposed agent can recommend the tourist a personalized travel route to enjoy Tainan City according to the tourist’s requirements.
It is also responsible for finding a suitable tour and plotting
this travel route on the Google map.
The tourist can follow the suggested personalized travel route to enjoy the cultural heritage and the local gourmet food
during his stay at Tainan City.
18
多媒體網路安全實驗室